# Learning Knowledge-based Prompts for Robust 3D Mask Presentation Attack Detection

arXiv: https://arxiv.org/abs/2505.03610 · HTML: https://mlsanity.com/paper/2505.03610/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 85 references that are in the map.
- First posted on arXiv 6 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [Unified Vision and Language Prompt Learning](https://mlsanity.com/paper/2210.07225/) (2022)
- [face anti-spoofing based on color texture analysis](https://mlsanity.com/paper/1511.06316/) (2015)
- [Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network](https://mlsanity.com/paper/1909.08848/) (2019)
- [CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing](https://mlsanity.com/paper/2003.05136/) (2020)
- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing](https://mlsanity.com/paper/1908.10654/) (2019)
- [FLIP: Cross-domain Face Anti-spoofing with Language Guidance](https://mlsanity.com/paper/2309.16649/) (2023)
- [On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing](https://mlsanity.com/paper/2011.08019/) (2020)
- [Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection](https://mlsanity.com/paper/2104.06148/) (2021)
- [TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection](https://mlsanity.com/paper/2104.07419/) (2021)
- [Multi-domain Learning for Updating Face Anti-spoofing Models](https://mlsanity.com/paper/2208.11148/) (2022)
- [CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing](https://mlsanity.com/paper/2403.14333/) (2024)
- [Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing](https://mlsanity.com/paper/2203.12175/) (2022)
- [Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition](https://mlsanity.com/paper/2303.15818/) (2023)
- [Deep Models and Shortwave Infrared Information to Detect Face Presentation Attacks](https://mlsanity.com/paper/2007.11469/) (2020)
- [Flexible-Modal Face Anti-Spoofing: A Benchmark](https://mlsanity.com/paper/2202.08192/) (2022)
- [FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing](https://mlsanity.com/paper/1904.09290/) (2019)
- [Visual Prompt Flexible-Modal Face Anti-Spoofing](https://mlsanity.com/paper/2307.13958/) (2023)
- [PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing](https://mlsanity.com/paper/2004.11744/) (2020)

## Built on by (most cited first, 2 of 2)

- [Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion](https://mlsanity.com/paper/2604.09018/) (2026)
- [Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing](https://mlsanity.com/paper/2608.17351/) (2026)

## Abstract (arXiv)

3D mask presentation attack detection is crucial for protecting face recognition systems against the rising threat of 3D mask attacks. While most existing methods utilize multimodal features or remote photoplethysmography (rPPG) signals to distinguish between real faces and 3D masks, they face significant challenges, such as the high costs associated with multimodal sensors and limited generalization ability. Detection-related text descriptions offer concise, universal information and are cost-effective to obtain. However, the potential of vision-language multimodal features for 3D mask presentation attack detection remains unexplored. In this paper, we propose a novel knowledge-based prompt learning framework to explore the strong generalization capability of vision-language models for 3D mask presentation attack detection. Specifically, our approach incorporates entities and triples from knowledge graphs into the prompt learning process, generating fine-grained, task-specific explicit prompts that effectively harness the knowledge embedded in pre-trained vision-language models. Furthermore, considering different input images may emphasize distinct knowledge graph elements, we introduce a visual-specific knowledge filter based on an attention mechanism to refine relevant elements according to the visual context. Additionally, we leverage causal graph theory insights into the prompt learning process to further enhance the generalization ability of our method. During training, a spurious correlation elimination paradigm is employed, which removes category-irrelevant local image patches using guidance from knowledge-based text features, fostering the learning of generalized causal prompts that align with category-relevant local patches. Experimental results demonstrate that the proposed method achieves state-of-the-art intra- and cross-scenario detection performance on benchmark datasets.